CT-based radiomics to predict development of macrovascular invasion in hepatocellular carcinoma:A multicenter study

Background:Macrovascular invasion(MaVI)occurs in nearly half of hepatocellular carcinoma(HCC)patients at diagnosis or during follow-up,which causes severe disease deterioration,and limits the possibility of surgical approaches.This study aimed to investigate whether computed tomography(CT)-based radiomics analysis could help predict development of MaVI in HCC.Methods:A cohort of 226 patients diagnosed with HCC was enrolled from 5 hospitals with complete MaVI and prognosis follow-ups.CT-based radiomics signature was built via multi-strategy machine learning methods.Afterwards,MaVI-related clinical factors and radiomics signature were integrated to construct the final prediction model(CRIM,clinical-radiomics integrated model)via random forest modeling.Cox-regression analysis was used to select independent risk factors to predict the time of MaVI development.Kaplan-Meier analysis was conducted to stratify patients according to the time of MaVI development,progression-free survival(PFS),and overall survival(OS)based on the selected risk factors.Results:The radiomics signature showed significant improvement for MaVI prediction compared with conventional clinical/radiological predictors(P<0.001).CRIM could predict MaVI with satisfactory areas under the curve(AUC)of 0.986 and 0.979 in the training(n=154)and external validation(n=72)datasets,respectively.CRIM presented with excellent generalization with AUC of 0.956,1.000,and 1.000 in each external cohort that accepted disparate CT scanning protocol/manufactory.Peel9_fos_InterquartileRange[hazard ratio(HR)=1.98;P<0.001]was selected as the independent risk factor.The cox-regression model successfully stratified patients into the high-risk and low-risk groups regarding the time of MaVI development(P<0.001),PFS(P<0.001)and OS(P=0.002).Conclusions:The CT-based quantitative radiomics analysis could enable high accuracy prediction of subsequent MaVI development in HCC with prognostic implications.

Characteristics and outcomes of hepatocellular carcinoma patients with macrovascular invasion following surgical resection: a meta-analysis of 40 studies and 8,218 patients

Background:Guidelines recommend that hepatocellular carcinoma(HCC)patients with portal vein tumor thrombosis(PVTT)and/or hepatic vein tumor thrombosis(HVTT)should undergo systemic therapy.However,recent data suggest that surgical resection may be beneficial in selected cases,but outcomes are heterogenous.We aimed to estimate pooled overall survival(OS),recurrence free survival(RFS)and complication rates in HCC patients with macrovascular invasion(MVI)following surgical resection.Methods:In this systematic review and meta-analysis,two investigators independently searched PubMed,Embase,and Cochrane databases from inception to Nov 10,2020,without language restrictions,for studies reporting outcomes of adult HCC patients with MVI who underwent liver resection with curative intent.Results:We screened 8,598 articles and included 40 studies involving 8,218 patients.Among all patients with MVI,the pooled median OS was 14.39 months[95%confidence interval(CI):10.99-18.84],1-year OS was 54.47%(95%CI:46.12-62.58%)and 3-year OS was 23.20%(95%CI:16.61-31.42%).Overall,1-and 3-year RFS were 27.70%(95%CI:21.00-35.57%)and 10.06%(95%CI:6.62-15.01%),respectively.Among patients with PVTT,median OS was 20.41 months in those with segmental/2nd order involvement compared to 12.91 months if 1st order branch was involved and 6.41 months if the main trunk was involved.The pooled rate of major complications was 6.17%(95%CI:3.53-10.56%).Conclusions:Overall median survival was 14.39 months for HCC patients with MVI following resection.Median survival was higher in PVTT with segmental/2nd order involvement at 20.41 versus 6.41 months if the main trunk was involved.